An evaluation of the impact of quality of life on government effectiveness using multicollinearity technique: evidence from Nigeria

Abstract

Studies have shown that researchers often face challenges in identifying and addressing multicollinearity effectively, which potentially lead to incorrect inferences. This study aims to detect the presence and impact of multicollinearity within a multiple linear regression model. It also intends to examine the effect of quality of life indicators on Government effectiveness in Nigeria. The data utilized in this study was the Government effectiveness and the quality of life (proxies by suicide mortality rate, self-employment, control of corruption, rule of law, government expenditure, military expenditure, life expectancy at birth, security of life and property, infant mortality rate, people using at least basic sanitation service, people using safety managed drinking water services, people using safely managed sanitation services and vulnerable employment between 2001 – 2021). The data was extracted from the World Development Indicators (WDI) database. The variance inflation factors (VIF), correlation matrices, and condition indices were employed to detect and address multicollinearity within the multiple linear regression model using stepwise method. Findings indicated that, most of the predictor variables were highly correlated with each other, except; suicide mortality, control of corruption, rule of law, general government final consumption expenditure, military expenditure and number of infant deaths, which were retained for the study. It was also revealed from the result that suicide mortality rate has a negative and insignificant influence while military expenditure and control of corruption was found to be positively and significantly related to government effectiveness at 5% significance level.